A Deep Learning Network based Robust Fault Diagnosis Method for IGBT Open Circuit

Yongjie Liu, Ariya Sangwongwanich, Yi Zhang, Rui Kong, Yingzhou Peng, Khalifa Al Hosani, Huai Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes an IGBT open-circuit fault diagnosis method that can maintain high accuracy under diverse operation conditions and circuit parameter variances. Different aspects of uncertainties are analyzed in the component parameters, operation conditions, and measurement errors of a three-phase inverter case study. A lightweight Convolutional Neural Network (CNN) is applied based on an obtained dataset covering a wide range of inverter operation scenarios and uncertainties. The comparisons with benchmarked conventional fault diagnosis method and with different machine learning methods are presented. The results verify the improved accuracy in open-circuit diagnosis considering complex operation conditions and meanwhile with reduced detection time in certain scenarios.

Original languageBritish English
Title of host publication2024 IEEE 10th International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2366-2371
Number of pages6
ISBN (Electronic)9798350351330
DOIs
StatePublished - 2024
Event10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia - Chengdu, China
Duration: 17 May 202420 May 2024

Publication series

Name2024 IEEE 10th International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

Conference

Conference10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia
Country/TerritoryChina
CityChengdu
Period17/05/2420/05/24

Keywords

  • dynamic operation conditions
  • IGBT open circuit fault diagnosis
  • lightweight convolutional neural network
  • robustness

Fingerprint

Dive into the research topics of 'A Deep Learning Network based Robust Fault Diagnosis Method for IGBT Open Circuit'. Together they form a unique fingerprint.

Cite this